Research on Machine Learning-Based Extraction and Classification of Crop Planting Information in Arid Irrigated Areas Using Sentinel-1 and Sentinel-2 Time-Series Data DOI Creative Commons

Lixiran Yu,

Hongfei Tao,

Qiao Li

и другие.

Agriculture, Год журнала: 2025, Номер 15(11), С. 1196 - 1196

Опубликована: Май 30, 2025

Irrigation areas in arid regions are vital production for grain and cash crops worldwide. Grasping the temporal spatial evolution of planting configurations across several years is crucial effective regional agricultural resource management. In view problems such as insufficient optical images caused by cloudy weather unclear spatiotemporal patterns structures irrigation over years, this study, we took Santun River Area, a typical region Xinjiang, China, an example. By leveraging long time-series remote sensing from Sentinel-1 Sentinel-2, spectral, index, texture, polarization features ground objects study area were extracted. When analyzing index characteristics, considered widely used global vegetation indices, including Normalized Difference Vegetation Index (NDVI), Enhanced (EVI), Soil Adjusted (SAVI), Global Environment Monitoring (GEMI). Additionally, integrated vertical–vertical vertical–horizontal data obtained synthetic aperture radar (SAR) satellite systems. Machine learning algorithms, random forest algorithm (RF), Classification Regression Trees (CART), Support Vector Machines (SVM), employed structure classification. The optimal classification model selected was subjected to inter-annual transfer obtain multiple years. research findings follows: (1) RF outperforms CART SVM algorithms terms accuracy, achieving overall accuracy (OA) 0.84 kappa coefficient 0.805. (2) cropland classified exhibited high degree consistency with statistical yearbook (R2 = 0.82–0.91). Significant differences observed estimated cotton, maize, tomatoes, wheat, while other not statistically significant. (3) From 2019 2024, cotton remained dominant crop, although its proportional fluctuated considerably, maize wheat tended remain stable, those tomato melon showed relatively minor changes. Overall, demonstrates cotton-dominated, stable cropping crops. newly developed framework exhibits exceptional precision categorization maintaining impressive adaptability, offering insights optimizing operations sustainable allocation irrigation-dependent zones.

Язык: Английский

Seasonal Land Use and Land Cover Mapping in South American Agricultural Watersheds Using Multisource Remote Sensing: The Case of Cuenca Laguna Merín, Uruguay DOI Creative Commons
Giancarlo Alciaturi, Shimon Wdowinski, María del Pilar García Rodríguez

и другие.

Sensors, Год журнала: 2025, Номер 25(1), С. 228 - 228

Опубликована: Янв. 3, 2025

Recent advancements in Earth Observation sensors, improved accessibility to imagery and the development of corresponding processing tools have significantly empowered researchers extract insights from Multisource Remote Sensing. This study aims use these technologies for mapping summer winter Land Use/Land Cover features Cuenca de la Laguna Merín, Uruguay, while comparing performance Random Forests, Support Vector Machines, Gradient-Boosting Tree classifiers. The materials include Sentinel-2, Sentinel-1 Shuttle Radar Topography Mission imagery, Google Engine, training validation datasets quoted methods involve creating a multisource database, conducting feature importance analysis, developing models, supervised classification performing accuracy assessments. Results indicate low significance microwave inputs relative optical features. Short-wave infrared bands transformations such as Normalised Vegetation Index, Surface Water Index Enhanced demonstrate highest importance. Accuracy assessments that various classes is optimal, particularly rice paddies, which play vital role country’s economy highlight significant environmental concerns. However, challenges persist reducing confusion between classes, regarding natural vegetation versus seasonally flooded vegetation, well post-agricultural fields/bare land herbaceous areas. Forests Trees exhibited superior compared Machines. Future research should explore approaches Deep Learning pixel-based object-based integration address identified challenges. These initiatives consider data combinations, including additional indices texture metrics derived Grey-Level Co-Occurrence Matrix.

Язык: Английский

Процитировано

1
Estimation of the aboveground carbon stocks based on tree species identification in Saihanba plantation forest DOI
Ao Zhang, Xiaohong Wang, Xin Gu

и другие.

Ecological Indicators, Год журнала: 2025, Номер 173, С. 113370 - 113370

Опубликована: Март 21, 2025

Язык: Английский

Процитировано

0
Exploring new mangrove horizons: A scalable remote sensing approach with Planet-NICFI and Sentinel-2 images DOI Creative Commons
Adam Irwansyah Fauzi, Markus Immitzer, Clement Atzberger

и другие.

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103152 - 103152

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Experimental studies to determine the maximum effort to extract containerized tree seedling from a cassette cell DOI Open Access
Kristina Chernik,

Sergey Eliseev

Forestry Engineering Journal, Год журнала: 2025, Номер 15(1), С. 138 - 153

Опубликована: Май 12, 2025

Reforestation works, including those with containerized tree seedling, are characterized by high labor and en-ergy consumption. Currently, planting seedling is carried out manually or the use of forest plant-ing machines aggregated tractors, where operator feeds seedlings into machine. When using automatic units on manipulators harvesters excavators, also extracted manually, indicating de-pendence human factor weaknesses technology. The relevance research to develop an auto-mated feeding system. object study this paper process extracting from cells cassettes. subject force arising during extraction cells. aim work determine a container-ized cassettes under given conditions, necessary for development automated system In work, influence parameters amount required extract cell was investigated. conducted basis universal testing machine UTS-110MN-30-0U, measurement each experiment recorded in real time. Results study: calculation effort Mathcad applied mathematical program performed; dependence root obtained; maximum minimum value re-quired determined experimentally. obtained results will be further used optimize selection actuating elements developed unit.

Язык: Английский

Процитировано

0
Research on Machine Learning-Based Extraction and Classification of Crop Planting Information in Arid Irrigated Areas Using Sentinel-1 and Sentinel-2 Time-Series Data DOI Creative Commons

Lixiran Yu,

Hongfei Tao,

Qiao Li

и другие.

Agriculture, Год журнала: 2025, Номер 15(11), С. 1196 - 1196

Опубликована: Май 30, 2025

Irrigation areas in arid regions are vital production for grain and cash crops worldwide. Grasping the temporal spatial evolution of planting configurations across several years is crucial effective regional agricultural resource management. In view problems such as insufficient optical images caused by cloudy weather unclear spatiotemporal patterns structures irrigation over years, this study, we took Santun River Area, a typical region Xinjiang, China, an example. By leveraging long time-series remote sensing from Sentinel-1 Sentinel-2, spectral, index, texture, polarization features ground objects study area were extracted. When analyzing index characteristics, considered widely used global vegetation indices, including Normalized Difference Vegetation Index (NDVI), Enhanced (EVI), Soil Adjusted (SAVI), Global Environment Monitoring (GEMI). Additionally, integrated vertical–vertical vertical–horizontal data obtained synthetic aperture radar (SAR) satellite systems. Machine learning algorithms, random forest algorithm (RF), Classification Regression Trees (CART), Support Vector Machines (SVM), employed structure classification. The optimal classification model selected was subjected to inter-annual transfer obtain multiple years. research findings follows: (1) RF outperforms CART SVM algorithms terms accuracy, achieving overall accuracy (OA) 0.84 kappa coefficient 0.805. (2) cropland classified exhibited high degree consistency with statistical yearbook (R2 = 0.82–0.91). Significant differences observed estimated cotton, maize, tomatoes, wheat, while other not statistically significant. (3) From 2019 2024, cotton remained dominant crop, although its proportional fluctuated considerably, maize wheat tended remain stable, those tomato melon showed relatively minor changes. Overall, demonstrates cotton-dominated, stable cropping crops. newly developed framework exhibits exceptional precision categorization maintaining impressive adaptability, offering insights optimizing operations sustainable allocation irrigation-dependent zones.

Язык: Английский

Процитировано

0